| 145 | 0 | 71 |
| 下载次数 | 被引频次 | 阅读次数 |
采用实验以及建立BP神经网络的方式,对拉拔理论公式进行验证,研究拉拔成形工艺的制定以及拉拔后焊缝对管材质量的影响。实验结果表明,对于304不锈钢焊管来说,单道次最大减径率为30.4%,伸长率最大为40%;拉拔力与减径率、工作带长度等影响因素成正相关,拉拔速度对拉拔力的影响不大;通过拉拔成形工艺能有效改善焊缝处的晶粒取向,使得管材沿拉拔方向有较好的成形性;建立BP神经网络训练模型,得到回归值R,表明该模型有较好的预测性,从而验证了模型的可行性。
Abstract：The drawing theoretical formula was verified by experiments and the establishment of BP neural networks, the development of the drawing process and the effect of the weld on the quality of the tube after drawing were studied. The experiment results show that for 304 stainless steel welded tube, the maximum diameter reduction rate in a single pass is 30. 4%, and the maximum elongation is 40%;the drawing force is positively correlated with influencing factors such as the diameter reduction rate and the length of the working belt, and the drawing speed has little effect on the drawing force. The grain orientation at the weld can be effectively improved through the drawing process, so that the tubes have better formability along the drawing direction. BP neural network training model was established to obtain the regression value R, which shows that the model has good predictability, thus verifying the feasibility of the model.
[1]毕宗岳,张万鹏.国内外油气管材技术现状与发展趋势[C]//第四届数控机床与自动化技术高层论坛.西安,2013:1.BI Zongyue, ZHANG Wanpeng. Current status and development trends of oil and gas pipe technology at home and abroad[C]//The 4th CNC Machine Tool and Automation Technology High-Level Forum. Xi′an, 2013:1.
[2]张万鹏,张锦刚,宋红兵,等.井下大功率电加热器制造工艺与应用[J].焊管, 2023, 46(9):33-40, 48.ZHANG Wanpeng, ZHANG Jingang, SONG Hongbing, et al. Manufacturing technology and application of underground highpower electric heaters[J]. Welded Pipe, 2023, 46(9):33-40, 48.
[3]谢玉洪,蔡东升,孙晗森.中国海油非常规气勘探开发一体化探索与成效[J].中国石油勘探, 2020, 25(2):27-32.XIE Yuhong, CAI Dongsheng, SUN Hansen. Exploration and achievements of integrated unconventional gas exploration and development by China national offshore oil corporation[J]. China Petroleum Exploration, 2020, 25(2):27-32.
[4]吴奇,胥云,王晓泉,等.非常规油气藏体积改造技术———内涵、优化设计与实现[J].石油勘探与开发, 2012, 39(3):352-358.WU Qi, XU Yun, WANG Xiaoquan, et al. Volume transformation technology for unconventional oil and gas reservoirs:Connotation,optimization design and implementation[J]. Petroleum Exploration and Development, 2012, 39(3):352-358.
[5]李国欣,朱如凯.中国石油非常规油气发展现状、挑战与关注问题[J].中国石油勘探, 2020, 25(2):1-13.LI Guoxin, ZHU Rukai. Current status, challenges and concerns of unconventional oil and gas development in China[J]. China Petroleum Exploration, 2020, 25(2):1-13.
[6]张伟玮,王仲仁,陈景松,等.无芯棒拉拔过程应力应变分析及壁厚变化[J].塑性工程学报, 2013, 20(2):29-32.ZHANG Weiwei, WANG Zhongren, CHEN Jingsong, et al.Stress, strain analysis and wall thickness changes during mandrelfree drawing process[J]. Journal of Plasticity Engineering, 2013,20(2):29-32.
[7] DJAVANROODI F, ZOLFAGHARI A A, EBRAHIMI M, et al.Equal channel angular pressing of tubular samples[J]. Acta Metallurgica Sinica(English Letters), 2013, 26(5):574-580.
[8]赵海凤,张远庆,谭振宇,等.钢丝拉拔过程中拉拔力检测[J].金属制品, 2020, 46(6):9-12.ZHAO Haifeng, ZHANG Yuanqing, TAN Zhenyu, et al. Pull-out force detection during wire drawing process[J]. Metal Products,2020, 46(6):9-12.
[9]欧阳斌,陈艳红,邓传军.基于PSO优化BP神经网络的露天矿边坡位移预测模型[J].有色金属:矿山部分, 2020,72(5):37-41.OUYANG Bin, CHEN Yanhong, DENG Chuanjun. Open-pit mine slope displacement prediction model based on PSO optimized BP neural network[J]. Nonferrous Metals(Mining Section), 2020,72(5):37-41.
[10]胡凡,彭亮,仵峰峰,等.基于BP神经网络模型的充填体强度值预测[J].有色金属:矿山部分, 2021, 73(6):60-65.HU Fan, PENG Liang, WU Fengfeng, et al. Prediction of filling body strength value based on BP neural network model[J]. Nonferrous Metals(Mining Section), 2021, 73(6):60-65.
[11]王敬龙,朱晓宇,王效岗.基于GA-BP神经网络板材辊式矫直工艺预测模型[J].现代制造工程, 2023,(8):115-120.WANG Jinglong, ZHU Xiaoyu, WANG Xiaogang. Prediction model of plate roller straightening process based on GA-BP neural network[J]. Modern Manufacturing Engineering, 2023,(8):115-120.
基本信息:
中图分类号:TG356
引用信息:
[1]王少华,宋红兵,张万鹏,等.矿物绝缘电缆连续管保护套拉拔成形工艺研究[J].塑性工程学报,2025(03):71-77.
基金信息:
中国石油天然气集团有限公司前瞻性基础性技术攻关项目(2022DJ1409)
2025-04-07
2025-04-07
2025-04-07